检索结果-南通市图书馆

3D Instance Segmentation Using Deep Learning on RGB-D Indoor Data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第9期72卷 5777-5791页

作者： siddiqui muhammad yasir Amin muhammad Sadiq Hyunsik Ahn Department of Robot System Engineering Tongmyong UniversityBusan48520Korea Department of Information&Technology University of Central PunjabLahorePakistan Department of Electronics Engineering Tongmyong UniversityBusan48520Korea

3D object recognition is a challenging task for intelligent and robot systems in industrial and home indoor *** is critical for such systems to recognize and segment the 3D object instances that they encounter on a frequent *** computer vision,graphics,and machine learning fields have all given it a lot of ***,3D segmentation was done with hand-crafted features and designed approaches that didn’t achieve acceptable performance and couldn’t be generalized to large-scale *** learning approaches have lately become the preferred method for 3D segmentation challenges by their great success in 2D computer ***,the task of instance segmentation is currently less *** this paper,we propose a novel approach for efficient 3D instance segmentation using red green blue and depth(RGB-D)data based on deep *** 2D region based convolutional neural networks(Mask R-CNN)deep learning model with point based rending module is adapted to integrate with depth information to recognize and segment 3D instances of *** order to generate 3D point cloud coordinates(x,y,z),segmented 2D pixels(u,v)of recognized object regions in the RGB image are merged into(u,v)points of the depth ***,we conducted an experiment and analysis to compare our proposed method from various points of view and *** experimentation shows the proposed 3D object recognition and instance segmentation are sufficiently beneficial to support object handling in robotic and intelligent systems.

关键词： Instance segmentation 3D object segmentation deep learning point cloud coordinates

Deep Learning-Based 3D Instance and Semantic Segmentation: A Review

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal on Artificial Intelligence 2022年第2期4卷 99-114页

作者： siddiqui muhammad yasir Hyunsik Ahn Department of Robot System Engineering Tongmyong UniversityBusan48520Korea School of Artificial Intelligence Tongmyong UniversityBusan48520Korea

The process of segmenting point cloud data into several homogeneous areas with points in the same region having the same attributes is known as 3D *** is challenging with point cloud data due to substantial redundancy,fluctuating sample density and lack of apparent *** research area has a wide range of robotics applications,including intelligent vehicles,autonomous mapping and navigation.A number of researchers have introduced various methodologies and *** learning has been successfully used to a spectrum of 2D vision domains as a prevailing ***,due to the specific problems of processing point clouds with deep neural networks,deep learning on point clouds is still in its initial *** study examines many strategies that have been presented to 3D instance and semantic segmentation and gives a complete assessment of current developments in deep learning-based 3D *** these approaches’benefits,draw backs,and design mechanisms are studied and *** study evaluates the impact of various segmentation algorithms on competitiveness on various publicly accessible datasets,as well as the most often used pipelines,their advantages and limits,insightful findings and intriguing future research directions.

关键词： Artificial intelligence computer vision robot vision 3D instance segmentation 3D semantic segmentation 3D data deep learning point cloud mesh voxel RGB-D segmentation

Modeling&Evaluating the Performance of Convolutional Neural Networks for Classifying Steel Surface Defects

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal on Artificial Intelligence 2022年第4期4卷 245-259页

作者： Nadeem Jabbar Chaudhry M.Bilal Khan M.Javaid Iqbal siddiqui muhammad yasir Department of Computer Science Superior UniversityLahorePakistan Department of Computer Science University of Central PunjabLahorePakistan Department of Mechanical System Engineering Tongmyong UniversityBusanKorea

Recently,outstanding identification rates in image classification tasks were achieved by convolutional neural networks(CNNs).to use such skills,selective CNNs trained on a dataset of well-known images of metal surface defects captured with an RGB *** must be detected early to take timely corrective action due to production *** image classification up till now,a model-based method has been utilized,which indicated the predicted reflection characteristics of surface defects in comparison to flaw-free *** problem of detecting steel surface defects has grown in importance as a result of the vast range of steel applications in end-product sectors such as automobiles,households,construction,*** processes for detections are time-consuming,labor-intensive,and *** strategies have been used to automate manual processes,but CNN models have proven to be the most effective rather than image processing andmachine learning *** using differentCNNmodels with fine-tuning,easily compare their performance and select the best-performing model for the same kinds of ***,it is important that using different CNN models either from fine tuning can be computationally expensive and ***,our study helps the upcoming researchers to choose the CNN without considering the issues of model complexity,performance,and computational *** this article,the performance of various CNN models like Visual Geometry Group,VGG16,VGG19,ResNet152,ResNet152V2,Xception,InceptionV3,InceptionResNetV2,NASNetLarge,MobileNetV2,and DenseNet201 with transfer learning techniques are *** models were chosen based on their popularity and impact in the field of computer vision research,as well as their performance on benchmark *** to the outcomes,DenseNet201 outperformed the other CNN models and had the greatest detection rate on the NEU dataset,falling in at 98.37 percent.

关键词： Convolutional neural network transfer learning defect detection

Inferior glenohumeral joint dislocation with greater tuberosity avulsion

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Traumatology 2015年第3期18卷 181-183页

作者： Mohd Faizan Latif Zafar Jilani Mazhar Abbas yasir Salam siddiqui Aamir Bin Sabir M.K.A. Sherwani Saifullah Khalid Department of Orthopaedic Surgery and Radiodiagnosis Jawaharlal Nehru Medical College Aligarh Muslim University Aligarh Uttar Pradesh 202002 India

Inferior glenohumeral dislocation is the least common type of glenohumeral dislocations. It may be associated with fractures of the adjacent bones and neurovascular compromise. It should be treated immediately by close reduction. The associated neuropraxia usually recovers with time. Traction-counter traction method is commonly used for reduction followed by immobilization of the shoulder for three weeks. Here, we report a case of inferior glenohumeral joint dislocation with greater tuberosity fracture with transient neurovascular compromise and present a brief review of the literature.

关键词： Shoulderjoint Shoulder dislocation Fractures bone